Claude + TikTok. Claude + OnlyFans. Claude + Google Maps. Claude + Shopify
All of them were built using these exact folders.
These 10 skills turn Claude from a smart chatbot into an autonomous development and design department
Frontend Design, Algorithmic Art, Systematic Debugging, Canvas Design, Theme Factory, Web Artifacts Builder, Superpowers, File Search, Context Optimization, and Skill Creator.
Skills > prompts. Every single time
AI is really wild—sometimes it feels like we're getting a glimpse into the future, and other times it’s like talking to a very smart, confused friend. What's your favorite AI moment?
READ THIS.
She is 22, closed a $21 million a16z round, and her AI is live inside Fortune 100 companies while most people her age are still deciding what to build.
Most people watching this will feel inspired for ten minutes and then do nothing with it.
My article gives you the practical version, 17 AI agent jobs that quietly add up to $10K a month with no funding required.
Full guide below.
Andrej Karpathy: "90% of Claude's mistakes come from missing context, not a weak model."
41% mistake rate without a CLAUDE.md. 11% with the 4-rule baseline. 3% with the 12-rule version below
here are the 12 rules senior engineers settled on:
1. think before coding: state assumptions, don't guess. the model can't read your mind, stop hoping it will
2. simplicity first: minimum code, no speculative abstractions. the moment you let Claude add "for future flexibility," you've added 200 lines you'll delete next quarter
3. surgical changes: touch only what you must. don't let it improve adjacent code, that's how PRs blow up
4. goal-driven execution: define success criteria upfront, loop until verified. without them Claude either loops forever or stops too early
5. use the model only for judgment calls: classification, drafting, summarization, extraction. NOT routing, retries, status-code handling, deterministic transforms. if code can answer, code answers
6. token budgets are not advisory: per-task 4000, per-session 30000. by message 40 of a long debug, Claude is re-suggesting fixes you rejected at message 5
7. surface conflicts, don't average them: two patterns in the codebase? pick one. Claude blending them is how errors get swallowed twice
8. read before you write: read exports, callers, shared utilities. Claude will happily add a duplicate function next to an identical one it never read
9. tests verify intent, not just behavior: a test that can't fail when business logic changes is wrong. all 12 of Claude's tests can pass while the function returns a constant
10. checkpoint every significant step: Claude finished steps 5 and 6 on top of a broken state from step 4. nobody noticed for an hour
11. match the codebase conventions: class components? don't fork to hooks silently. testing patterns assumed componentDidMount, hooks broke them without surfacing
12. fail loud: "completed successfully" with 14% of records silently skipped is the worst class of bug. surface uncertainty, don't hide it
what actually compounds instead of the next framework:
- the CLAUDE.md file as institutional memory across sessions
- eval-driven changes, not vibe-driven
- checkpoints over speed
- explicit conflicts over silent blending
- discipline over framework, every time
- one repo, one rules file, no exceptions
you don't need a better AI
you need better context engineering
complete playbook below ↓
KARPATHY JUST HANDED EVERY DEVELOPER THE EXACT FILE CLAUDE CODE NEEDED FROM DAY ONE.
65 lines. 110K stars. the cheat code for every broken workflow you've been blaming on the model.
if I had this a year ago, I would've shipped twice as fast.
make sure to bookmark it before it gets lost in your feed.
I was losing 2 hours a day to Claude rewriting code I didn't ask it to touch.
then I found CLAUDE. md.
90 seconds to set up. changed everything.
Karpathy identified 4 failure patterns Claude Code repeats constantly, in his own words:
→ silent assumptions: Claude makes decisions without checking with you
→ code bloat: 1000 lines written when 100 would do
→ collateral damage: Claude edits code unrelated to the task
→ no success criteria: Claude loops with no finish line
these aren't model failures. they're missing instructions.
CLAUDE. md gives Claude the 4 rules it needed from day one:
→ think before coding, state assumptions. ask before assuming.
→ simplicity first, minimum code. nothing speculative.
→ surgical changes, touch only what is required. nothing adjacent.
→ goal-driven execution, define success before starting. loop until verified.
65 lines. no build step. no framework. no dependencies.
just the 4 principles every developer already knew, but needed Karpathy to write down.
ClaudeKit is the only team you need to build something like this (https://t.co/aW94IVKzGN)
the guide on how to learn Claude below (every resource you need)
https://t.co/8pon0x7bcI
Both men said “I can’t breathe”, but only one man’s death was covered relentlessly by the media.
The only conclusion that can be drawn is that the legacy mainstream media is incredibly, hatefully racist against Whites.
Don't upgrade to the $100 Claude plan (yet).
These 21 hacks make the $20/month plan enough:
1. You upload PDFs raw. One page = 3,000 tokens.
Fix: Paste the text into a Google doc. Download as .md format. Under 200 tokens.
2. You build files inside Cowork too early.
Fix: Plan in Chat first. Move to Cowork only when you know exactly what you want.
3. You write 500-word prompts that reload.
Fix: Write 29 words instead: "I want to [task] to [goal]. Ask me questions using AskUserQuestion."
4. You say "redo the whole thing" to fix section 3.
Fix: "Only redo section 3. Keep everything else. No commentary. Just the output."
5. You send 3 separate messages for 3 tasks.
Fix: One message, three tasks. "Summarize this, list the points, suggest a headline."
6. You type "No, I meant," stacking on the history.
Fix: Click 'Edit' on your original message. Fix it. Regenerate.
7. You rewrite prompts from scratch every time.
Fix: Keep a prompt library. Same structure, swap the variable.
8. You use Opus for a simple grammar check.
Fix: Sonnet for quick tasks. Save Opus + Extended Thinking for deep work.
9. Your about-me file is 22,000 words (too long).
Fix: Trim to under 2,000 words. End sessions with "Write a session-notes .md."
Paste my .md file prompt: https://t.co/LyV7fegv4c
10. You never restart & keep stacking long chats.
Fix: When Cowork goes sideways, click "Restart the conversation from here" on an earlier message.
11. You never summarize before things get long.
Fix: Every 15-20 messages → summarize, copy the brief, start a fresh session.
12. You use Projects for recurring files.
Fix: Use Projects. Upload once. Every chat inside references it without re-burning tokens.
13. You dump 50 files into Cowork "just in case."
Fix: Only include what this task needs. Zero folders for quick tasks like email drafts.
14. You keep 3 topics in 1 chat. Claude re-reads all.
Fix: New topic = new chat. Always. Dead context is dead tokens.
15. You leave search & connectors on by default.
Fix: Default everything off. Turn features on per task, not per account.
16. You manually run the same report every week.
Fix: Use /schedule. "Every Monday at 7am, create my weekly briefing."
17. You let Claude Code explore your whole repo.
Fix: Be specific. "Build a bar chart from this CSV. Save as chart .png."
18. You skip Personal Preferences & waste setup.
Fix: Settings → Personal Preferences. Set your tone and style once.
19. You type lazy prompts like "make it better."
Fix: Speak your prompts with wispr .ai. Richer context in one shot.
20. You burn your whole limit in one morning.
Fix: Claude runs on a rolling 5-hour window. Split it.
21. You use Claude for things it can't do.
Fix: Know your tools. Images → Gemini.
Real-time search → Grok.
To download my exact .md files:
1. Go to https://t.co/psB7XxAv8w.
2. Subscribe for free. Open my welcome email.
3. Hit the automatic reply button inside.
4. Go to the Notion link in the second mail.
5. Copy-paste prompts, too.
The news today is a mix of inspiring stories and tough realities. It's a reminder that there's so much happening around us, both good and bad. Stay informed and engaged!
The South African laws are literally super racist, plain and simple.
It’s not complicated: imagine if the law was called “White Empowerment”, instead of “Black Empowerment”! People would have a seizure 😂
South Africa now has more anti-White laws than Apartheid had anti-Black laws. Think about that for a second …
The current South African government has objectively implemented Apartheid 2.0. Shame on them.
Isn't it wild how technology evolves so rapidly? Just when you think you've seen it all, something new comes along and blows your mind. Can't wait to see what’s next!
There’s something magical about discovering an old song that perfectly matches your mood. It’s like finding a forgotten treasure that instantly takes you back in time. 🎶
Congrats to Coach Rue and our Boys Golf Team on winning the STATE CHAMPIONSHIP today! We had no doubt they were the best in the state and they proved it today! AMAZING! ⛳️ @BravesScores @PublicMonroe@bravesof19@WHSbraves2020
I am blessed to announce that I have committed to play baseball and further my education at the University of Notre Dame #GoIrish#PlayLikeAChampionToday☘️
The Sun Newspapers (20 papers that cover more than 20 high schools) are naming Fall Athletes of the Year for the first time in 2018 for each of the nine sports. @WilliamstownHS has a winner in Wade Inge: https://t.co/xVJbfmiQXk